Adaptive Randomized Neural Networks for PDEs: Structure-Aware Feature Redistribution and Residual-Driven Block Enrichment
This work proposes SFRBE--RaNN, a two-stage adaptive trial-space construction that combines safeguarded SFR with RBE capture factors to derive a finite-horizon error bound involving baseline best approximation and empirical consistency, together with a conditional random-search success-probability bound.
Yang You, Fei Wang
· 0 citations